search

scalesim-project / scale-sim-v2

Repository to host and maintain scale-sim-v2 code
MIT License
232 stars 99 forks source link

Multiple Cores #101

Open V-Run-P opened 8 months ago

V-Run-P commented 8 months ago

Hello, I am trying to run Yolo topology with an 8MB SRAM buffer each for Input, Output, and Filter .i.e a total of 24MB SRAM. It takes a long time to execute just the first layer.

I have the following questions:

  1. Is there a way I can estimate the runtime memory required?
  2. Can we run the simulation on multiple cores? I see a comment on Line 69 of Simulator.py about parallelizable.

2. Run each layer

TODO: This is parallelizable

zhouwq13 commented 7 months ago

Hello, I am trying to run Yolo topology with an 8MB SRAM buffer each for Input, Output, and Filter .i.e a total of 24MB SRAM. It takes a long time to execute just the first layer.

I have the following questions:

  1. Is there a way I can estimate the runtime memory required?
  2. Can we run the simulation on multiple cores? I see a comment on Line 69 of Simulator.py about parallelizable.

2. Run each layer

TODO: This is parallelizable

Hi, have you solved this problem? Please contact me, Thanks in advance!